© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11285
    Prev
    Next
    INDEX
    Explanations

    Hasan, Lanza, trustees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è§ļ
    -0.10
    kits
    -0.09
    çĶ»çĶ»
    -0.08
    æĬķ产
    -0.08
     Terrace
    -0.08
    æªIJ
    -0.08
    èIJģ
    -0.08
    åĨ¼
    -0.08
    æĪIJ为ä¸ĢåIJį
    -0.08
    è°ģèĥ½
    -0.08
    POSITIVE LOGITS
    亲
    0.09
    çľ¼éĩĮ
    0.08
    urse
    0.08
    éĻĽä¸ĭ
    0.08
    amat
    0.08
    unched
    0.08
    çĬ¯
    0.08
    رج
    0.08
    åŃº
    0.08
    ä»Ĺ
    0.08
    Activations Density 0.002%

    No Known Activations